Article
Computer Science, Artificial Intelligence
Ayan Seal, Rishabh Bajpai, Mohan Karnati, Jagriti Agnihotri, Anis Yazidi, Enrique Herrera-Viedma, Ondrej Krejcar
Summary: This study presents a dataset that includes EEG data and Patient Health Questionnaire scores for the diagnosis and classification of depression. The results demonstrate the effectiveness of traditional supervised machine learning algorithms and feature selection methods in distinguishing healthy subjects from depressed individuals.
APPLIED INTELLIGENCE
(2023)
Article
Astronomy & Astrophysics
Neil Bassett, David Rapetti, Keith Tauscher, Bang D. Nhan, David D. Bordenave, Joshua J. Hibbard, Jack O. Burns
Summary: The investigation highlights the importance of considering the horizon in modeling low-frequency observations for global 21 cm signals. It shows that fitting data with multi-spectrum models can reduce bias and uncertainty in signal extraction, but accurately modeling the horizon's time dependence is crucial for a good fit.
ASTROPHYSICAL JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Gulay Tasci, Hui Wen Loh, Prabal Datta Barua, Mehmet Baygin, Burak Tasci, Sengul Dogan, Turker Tuncer, Elizabeth Emma Palmer, Ru-San Tan, U. Rajendra Acharya
Summary: This study presents a computationally lightweight handcrafted classification model for accurate detection of major depressive disorder (MDD) using electroencephalogram (EEG) signals. The model extracts local textural features and statistical features from the raw EEG signal and applies feature selection and classification algorithms to optimize the model. The generated model achieves high accuracies and outperforms other models developed using the same dataset.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Neurosciences
Nikhil Garg, Rohit Garg, Apoorv Anand, Veeky Baths
Summary: This paper focuses on classifying emotions on the valence-arousal plane using various feature extraction, feature selection, and machine learning techniques. A novel feature ranking technique and incremental learning approach are proposed, and the importance of different electrode locations is calculated. The collected dataset and pipeline are also published.
FRONTIERS IN HUMAN NEUROSCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Sina Shafiezadeh, Gian Marco Duma, Giovanni Mento, Alberto Danieli, Lisa Antoniazzi, Fiorella Del Popolo Cristaldi, Paolo Bonanni, Alberto Testolin
Summary: There is a growing interest in using artificial intelligence techniques for predicting epileptic seizures. Machine learning algorithms can extract statistical regularities from electroencephalographic (EEG) time series to anticipate abnormal brain activity. However, evaluating the performance of predictive models is challenging, as the use of questionable cross-validation schemes can introduce correlated signals into the training and test sets. This study demonstrates the importance of rigorous evaluation protocols in ensuring the generalizability of predictive models.
APPLIED SCIENCES-BASEL
(2023)
Article
Acoustics
Zelin Qiu, Jianjun Gu, Dingding Yao, Junfeng Li, Yonghong Yan
Summary: In this paper, a novel time-frequency neuro-steered speaker extractor (TF-NSSE) is proposed. It leverages time-frequency transformation to match the temporal resolution of speech signals with neural signals, significantly reducing computational complexity. Additionally, an interaction module is introduced to effectively fuse attention information and address the issue of insufficient data. Experimental results demonstrate that TF-NSSE outperforms existing time-domain methods in terms of extraction performance and resource consumption.
Article
Engineering, Electrical & Electronic
Aarti Sharma, Jaynendra Kumar Rai, Ravi Prakash Tewari
Summary: By analyzing the features of electroencephalogram signals, potential electrodes for detecting schizophrenia were successfully identified with 100% accuracy.
IETE JOURNAL OF RESEARCH
(2022)
Article
Neurosciences
Alonso Zea Vera, Ernest V. Pedapati, Travis R. Larsh, Kevin Kohmescher, Makoto Miyakoshi, David A. Huddleston, Hannah S. Jackson, Donald L. Gilbert, Paul S. Horn, Steve W. Wu
Summary: This study investigated the oscillatory changes in the right frontal lobe during motor inhibition in individuals with chronic tic disorders. The findings suggest that individuals with chronic tic disorders show greater event-related desynchronization in the right superior, middle, and inferior frontal gyral, which is associated with lower tic severity.
Article
Automation & Control Systems
Jan Rabcan, Vitaly Levashenko, Elena Zaitseva, Miroslav Kvassay
Summary: This article discusses a fuzzy classifier-based approach for EEG signal classification. The results of the study indicate that fuzzy classifiers are effective tools for EEG signal classification and achieve the highest classification accuracy.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Yaochong Li, Ri-Gui Zhou, Ruiqing Xu, Jia Luo, She-Xiang Jiang
Summary: This article investigates a hierarchic quantum mechanics-based framework for feature extraction and classification in electroencephalogram (EEG) signals. The framework prepares classical EEG signal dataset as a quantum state and utilizes quantum wavelet packet transformation for feature extraction. An improved quantum support vector machine is employed for classification and prediction. Experimental results show the feasibility and validity of the framework, which provides exponential speedup over classical counterparts.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Article
Multidisciplinary Sciences
Asif Ali Laghari, Yanqiu Sun, Musaed Alhussein, Khursheed Aurangzeb, Muhammad Shahid Anwar, Mamoon Rashid
Summary: This study proposes a deep residual-dense network based on bidirectional recurrent neural network (RNN) model for atrial fibrillation detection. By simplifying the feature extraction steps and utilizing the attention mechanism to fuse features, accurate detection of atrial fibrillation is achieved.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Electrical & Electronic
Simon Geirnaert, Servaas Vandecappelle, Emina Alickovic, Alain de Cheveigne, Edmund Lalor, Bernd T. Meyer, Sina Miran, Tom Francart, Alexander Bertrand
Summary: The article discusses the challenges faced by individuals with hearing impairment in conversation scenarios with multiple speakers and introduces the use of EEG technology to determine auditory attention focus and develop EEG-based AAD algorithms.
IEEE SIGNAL PROCESSING MAGAZINE
(2021)
Article
Chemistry, Analytical
Xavier Duart, Eduardo Quiles, Ferran Suay, Nayibe Chio, Emilio Garcia, Francisco Morant
Summary: The study compared white, red, and green flashing stimuli at three frequencies (5, 12, and 30 Hz) to find that the middle frequency generated the best SNR. White showed as good an SNR as red at 12 Hz, and green at 5 Hz. There was a correlation between attention and SNR at low frequency.
Article
Engineering, Biomedical
Yikai Gao, Aiping Liu, Lanlan Wang, Ruobing Qian, Xun Chen
Summary: This study proposes a self-interpretable deep learning model for patient-specific epileptic seizure prediction. The model measures the similarity between inputs and prototypes to make predictions, providing a transparent reasoning process and decision basis. Different sizes are assigned to prototypes in latent space to capture multi-scale features of EEG signals. The proposed model achieves state-of-the-art performance with self-interpretable evidence on two public epileptic EEG datasets.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Materials Science, Multidisciplinary
Chengcheng Zhang, Mingji Li, Xiuwei Xuan, Baozeng Zhou, Penghai Li, Hongji Li
Summary: Nitrogen-doped graphene microtubes synthesized by chemical vapor deposition have the potential to record high-density electroencephalography (EEG) signals. Microtubes with an N-content of 2.22% show low scalp-contact resistance and high signal-to-noise ratio of EEG signals. An EEG sensor with 72 optimized nitrogen-doped graphene microtubes is assembled to easily record spontaneous and visually evoked EEG signals. The sensor is convenient to wear and can identify high-density EEG signals, making it suitable for both peripheral fine control of motion imagination and clinical diagnosis of functional disorders in various brain regions, thereby promoting the development of healthcare electronics.
ADVANCED MATERIALS TECHNOLOGIES
(2023)
